Caveat verdict

corveil-dev

corveil

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

Accesses credentials AND makes external network calls

Reconfigures the agent to route all LLM API requests through the Corveil local proxy which fully logs, tracks, and analyzes every request, meaning all conversation data flows through a third-party system.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

25
security
50
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (1)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="$CORVEIL_KEY

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 2 system binaries. (1 elevated: curl).

network_outcredential_access
Check another skill Browse the registry Auditing your own skills or configs? Use the API